OmniVLA: Physically-Grounded Multimodal VLA with Unified Multi-Sensor Perception for Robotic Manipulation

作者：Heyu Guo, Shanmu Wang, Ruichun Ma, Shiqi Jiang, Yasaman Ghasempour, Omid Abari, Baining Guo, Lili Qiu · 单位：Princeton University, University of California, Los Angeles, Microsoft Research Asia · 会议/期刊：ICRA 2026 · 日期：2025-11-03 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / Other Modalities / Infrared/Thermal